Research Engineer Intern - Environments, Data and Post-Training
San Francisco • Intern
Posted 1d ago
Remote Work Policy
On-site
Employment Type
Intern
Categories
AI Research Engineer
About the job
Mercor is a leading AI data company that organizes human intelligence to power the AI economy. We build the layer between human expertise and frontier models, enabling millions of domain experts to train AI models. Our mission is to create a new category of work where expertise drives AI advancement, requiring an ambitious and fast-paced team working alongside researchers and AI companies at the forefront of technological change. Mercor is a profitable Series C company valued at $10 billion.
As a Research Engineer Intern, you will work at the intersection of engineering and applied AI research. Your contributions will directly impact post-training, RLVR, synthetic data generation, and large-scale evaluation workflows for frontier language models. The work you do will be instrumental in training LLMs to master tool use, agentic behavior, and real-world reasoning in production environments. You will shape rewards, conduct post-training experiments, and develop scalable systems to enhance model performance, while also designing and evaluating datasets, creating data augmentation pipelines, and building rubrics and evaluators to push the boundaries of LLM learning.
Responsibilities
- Work on post-training and RLVR pipelines to understand the impact of datasets, rewards, and training strategies on model performance.
- Design and run reward-shaping experiments and algorithmic improvements (e.g., GRPO, DAPO) to enhance LLM tool-use, agentic behavior, and real-world reasoning.
- Quantify data usability, quality, and performance uplift on key benchmarks.
- Build and maintain scalable data generation and augmentation pipelines.
- Create and refine rubrics, evaluators, and scoring frameworks for training and evaluation.
- Build and operate LLM evaluation systems, benchmarks, and metrics at scale.
- Collaborate with AI researchers, applied AI teams, and data producers.
- Operate within a fast-paced, experimental research environment with rapid iteration and high ownership.
Requirements
- Strong applied research background, with a focus on post-training and/or model evaluation.
- Strong coding proficiency and hands-on experience with machine learning models.
- Solid understanding of data structures, algorithms, backend systems, and core engineering fundamentals.
- Familiarity with APIs, SQL/NoSQL databases, and cloud platforms.
- Ability to reason deeply about model behavior, experimental results, and data quality.
- Excitement to work in person five days a week in a high-intensity, high-ownership environment.
Benefits
- $1.5K monthly stipend for meals
- Free Equinox membership
- $200 monthly laundry reimbursement
- $200 monthly personal wellness reimbursement